The Role of Virtual MCP in Managing LLM Costs
Agentic workflows can multiply LLM costs. Explore how Virtual MCP in agentgateway simplifies MCP management while reducing token consumption through centralized tool discovery, filtering, and governance.
agentgateway
Technical Blog
the-role-of-virtual-mcp-in-managing-llm-costs
Five Things We Noticed at AI Engineer World's Fair (That Have Nothing to Do With Our Booth)
AI Engineer World's Fair revealed where enterprise AI adoption really stands. Discover the biggest trends from the expo floor - from open source and production AI to Virtual MCP, cost visibility, and the governance challenges teams are facing today.
five-things-we-noticed-at-ai-engineer-worlds-fair-that-have-nothing-to-do-with-our-booth
Zero-Trust Agents for Autonomous Networks: winning Best Moonshot Catalyst at DTW Ignite 2026
zero-trust-agents-for-autonomous-networks-winning-best-moonshot-catalyst-at-dtw-ignite-2026
Federating Azure AI Foundry Agents with agentregistry
As AI agents multiply, governance becomes critical. Learn how to use agentregistry with Microsoft Foundry to discover, inventory, and manage agents across your environment.
federating-azure-ai-foundry-agents-with-agentregistry
Semantic Caching: Caching Meaning, Not Strings, for LLM Workloads
Why the next generation of LLM infrastructure cares about what a request means, not just how it’s spelled, and what that changes about cost, latency, and the place caching belongs in the stack.
semantic-caching-caching-meaning-not-strings-for-llm-workloads
Is a Pod the Right Deployment Unit for an AI Agent?
Are AI agents best deployed as Kubernetes Pods? Explore why agent-substrate introduces a new execution model built for scalable, ephemeral AI agents.
is-a-pod-the-right-deployment-unit-for-an-ai-agent
Context Compression vs. Compaction: Stop Treating Context as One Thing
Compaction is what an agent does when it runs out of memory. Compression is what infrastructure does so agents don’t have to. They sound similar, they live in different layers, and conflating them is why most teams reach for the crudest option first.
context-compression-vs-compaction-stop-treating-context-as-one-thing
What 'is' Agent Identity? Human? Workload? A new Layer?
In previous posts, I’ve covered the reasons why an AI agent needs an identity. I recommend reading that first. In this post I want to nail down “what is agent identity” because I’ve seen a lot of different interpretations from smart people such as “use OAuth” to “it’s just workload identity”, and new protocols cropping up, etc. But what “is” an agent identity in concrete terms?
what-is-agent-identity-human-workload-a-new-layer
APIs For Your Agents With Code Mode
Learn how to configure and test agentgateway Code Mode to expose APIs as MCP tools, enabling secure agent access without an MCP server.
apis-for-your-agents-with-code-mode
Why Sandboxing Your Agent Is Not Enough
What’s the difference between agent-sandbox and agent-substrate? Learn how these complementary projects help teams build AI agent platforms that are both secure and scalable on Kubernetes.
why-sandboxing-your-agent-is-not-enough
